Skill

cross-agent-review

Requests an independent code/PR/plan review from a different AI agent backend (e.g., Codex reviewing Claude's work) via the repowire mesh. Use for unbiased second opinions before merging.

code-quality

npx claudepluginhub prassanna-ravishankar/repowire --plugin repowire

Popularity

Stars

161

Forks

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/repowire:cross-agent-review

User invocable

Model invocable

Inline context

Default effort

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

Ask a peer running a **different** agent backend to review your work, so the

SKILL.md

43 lines · ~480 tokens

Similar Skills

code-review

Multi-agent code review with parallel specialized reviewers, architecture validation, and challenge validation. Automatically activates on PRs, branches, diffs, and review requests.

4 files

python

cross-model-review

Enables cross-model code review where a different AI model reviews code written by the current model, reducing self-approval bias. Provides patterns and rules for using Claude Code and Codex CLIs.

1 file

hyperskills

review-loop

Runs cross-LLM iterative code reviews with Codex or Gemini CLI peers, applying accepted fixes until consensus on improved code and report.

5 files

harness-engineering-skills

Stats

LanguagePython

Stars161

Forks29

MaintenanceExcellent

Last CommitJun 2, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Stats

Actions

Help us improve

Share bugs, ideas, or general feedback.

Cross-agent review

Ask a peer running a different agent backend to review your work, so the review is genuinely independent (not the same model checking itself).

Resolve the reviewer backend

Pick the reviewer in this order:

Explicit argument — if the user named a backend (e.g. "review with codex"), use it.

Configured default — else read it:

repowire config get skills.default_reviewer_backend

(Prints the value, or nothing if unset. --json for the raw value.)

Safe fallback — if still unset, pick any online peer whose backend differs from yours, or ask the user which backend to use. Never default to your own backend — that defeats the purpose. Never hardcode a specific backend.

You can see who is available and on which backend:

MCP: list_peers()

CLI: repowire peer list

Run the review

Find (or spawn) a peer on the chosen backend.

Send it a review request with the concrete diff/PR/plan to review. Be specific about what to check.

MCP: ask(peer_name, "Review this diff for correctness + bugs: <context>")
The tracked ask/ack lifecycle is MCP-only — there's no CLI equivalent for a non-blocking ask (repowire peer ask is a synchronous test utility, not this).

ask is non-blocking and returns a correlation_id. The reviewer closes the thread with ack(corr_id, <their review>) — that reply comes back to you.

Apply the review; iterate with ask(reply_to=corr_id, ...) for follow-ups.

If no different-backend peer is available and the user wants one, spawn it (see the delegate skill) — but only with the user's go-ahead.